Sökning: "Partitioning Optimization Design"
Visar resultat 1 - 5 av 6 uppsatser innehållade orden Partitioning Optimization Design.
1. Complexity Analysis and Structural Optimization for Architecture Models of Mechatronic Systems
Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)Sammanfattning : The design and development of mechatronic system are becoming an increasingly complex task due to the numerous disciplines involved, rapidly increasing scales, and the integration issues of different domains and technologies. The structural complexity of the architecture model design decides the quality of system design in many aspects: the scalability of the system design; usage of allocated resources which influences the computational overhead, etc. LÄS MER
2. A BINARY SPACE PARTITIONED ANT COLONY OPTIMIZATION ALGORITHM FOR THE TRAVELING SALESMAN PROBLEM
Kandidat-uppsats, Mälardalens högskola/Akademin för innovation, design och teknikSammanfattning : A common type of problems that exist in both industrial and scientific spaces are optimization problems. These problems can be found in among other things manufacturing, pathfinding, network routing and more. Because of the wide area of application, optimization is well a studied area. LÄS MER
3. A Study on Efficient Memory Utilization in Machine Learning and Memory Intensive Systems
Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknikSammanfattning : As neural networks find more and more practical applications targeted for edge devices, the implementation of energy-efficient architectures is becoming very crucial. Despite the advancements in process technology, power and performance of memories remain to be a bottleneck for most computing platforms. LÄS MER
4. On using a zero lower bound on the physical density in Material DistributionTopology Optimization
Master-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : Material distribution topology optimization methods aim to place optimally material within a given domain or space. These methos use a socalled material indicator function r to determine for each point within the design domain whether it contains material (r 1) or void (r 0). LÄS MER
5. FPGA Hardware Acceleration of Inception Style Parameter Reduced Convolution Neural Networks
Master-uppsats, KTH/Skolan för informations- och kommunikationsteknik (ICT)Sammanfattning : Some researchers have noted that the growth rate in the number of network parameters of many recently proposed state-of-the-art CNN topologies is placing unrealistic demands on hardware resources and limits the practical applications of Neural Networks. This is particularly apparent when considering many of the projected applications (IoT, autonomous vehicles, etc) utilize embedded systems with even greater restrictions on computation and memory bandwidth than the typical research-class computer cluster that the CNN was designed on. LÄS MER